Python: feat: add Amazon Bedrock Knowledge Base tool and context provider

python/packages/bedrock/AGENTS.md

@@ -8,6 +8,8 @@ Integration with AWS Bedrock for LLM inference.
 - **`BedrockChatOptions`** - Options TypedDict for Bedrock-specific parameters
 - **`BedrockGuardrailConfig`** - Configuration for Bedrock guardrails
 - **`BedrockSettings`** - Pydantic settings for Bedrock configuration
+- **`BedrockKnowledgeBaseProvider`** - The public entry point for using an Amazon Bedrock Knowledge Base with an agent. A single `ContextProvider` with a `mode`: `"inject"` (inject retrieved passages as context), `"tool"` (expose a KB search tool the model can call), or `"both"` (default). Uses agentic retrieval (query decomposition + managed reranking) with fallback to standard Retrieve, and injects image/audio/video passages as multi-modal `Content`.
+- **`BedrockKnowledgeBaseSettings`** - Settings TypedDict for KB region/credentials resolution (`BEDROCK_*`)
 
 ## Usage
 

python/packages/bedrock/README.md

@@ -17,3 +17,10 @@ See the [Bedrock sample](../../samples/02-agents/providers/amazon/bedrock_chat_c
 - Loads credentials from the `BEDROCK_*` environment variables
 - Instantiates `BedrockChatClient`
 - Sends a simple conversation turn and prints the response
+
+### Knowledge Base Examples
+
+For Amazon Bedrock managed Knowledge Base retrieval, see:
+
+- [`bedrock_kb_tool.py`](../../samples/02-agents/providers/amazon/bedrock_kb_tool.py) — `BedrockKnowledgeBaseTool` as a `FunctionTool` the agent calls on demand.
+- [`bedrock_kb_context_provider.py`](../../samples/02-agents/providers/amazon/bedrock_kb_context_provider.py) — `BedrockKnowledgeBaseProvider` as a `ContextProvider` that injects KB context automatically.

python/packages/bedrock/agent_framework_bedrock/__init__.py

@@ -4,6 +4,8 @@
 
 from ._chat_client import BedrockChatClient, BedrockChatOptions, BedrockGuardrailConfig, BedrockSettings
 from ._embedding_client import BedrockEmbeddingClient, BedrockEmbeddingOptions, BedrockEmbeddingSettings
+from ._knowledge_base import BedrockKnowledgeBaseSettings
+from ._knowledge_base_provider import BedrockKnowledgeBaseProvider
 
 try:
     __version__ = importlib.metadata.version(__name__)
@@ -17,6 +19,8 @@
     "BedrockEmbeddingOptions",
     "BedrockEmbeddingSettings",
     "BedrockGuardrailConfig",
+    "BedrockKnowledgeBaseProvider",
+    "BedrockKnowledgeBaseSettings",
     "BedrockSettings",
     "__version__",
 ]